def download(d):
"""Binds voxforge_url, archive_dir, total, and counter into this scope
Downloads the given file
:param d: a tuple consisting of (index, file) where index is the index
of the file to download and file is the name of the file to download
"""
(i, file) = d
download_url = voxforge_url + "/" + file
c = counter.increment()
print("Downloading file {} ({}/{})...".format(i + 1, c, total))
maybe_download(filename_of(download_url), archive_dir, download_url)
def maybe_download_language(language):
lang_upper = language[0].upper() + language[1:]
return maybe_download(
SWC_ARCHIVE.format(language=lang_upper),
CLI_ARGS.base_dir,
SWC_URL.format(language=lang_upper),
)
def _download_and_preprocess_data(target_dir):
# Making path absolute
target_dir = os.path.abspath(target_dir)
# Conditionally download data
archive_path = maybe_download(ARCHIVE_NAME, target_dir, ARCHIVE_URL)
# Conditionally extract data
_maybe_extract(target_dir, ARCHIVE_DIR_NAME, archive_path)
# Produce CSV files
_maybe_convert_sets(target_dir, ARCHIVE_DIR_NAME)
def _download_and_preprocess_data(target_dir):
# Making path absolute
target_dir = os.path.abspath(target_dir)
# Conditionally download data
archive_path = maybe_download(ARCHIVE_NAME, target_dir, ARCHIVE_URL)
# Conditionally extract common voice data
_maybe_extract(target_dir, ARCHIVE_DIR_NAME, archive_path)
# Conditionally convert common voice CSV files and mp3 data to DeepSpeech CSVs and wav
_maybe_convert_sets(target_dir, ARCHIVE_DIR_NAME)
def _download_and_preprocess_data(data_dir):
# Conditionally download data
LDC93S1_BASE = "LDC93S1"
LDC93S1_BASE_URL = "https://catalog.ldc.upenn.edu/desc/addenda/"
local_file = maybe_download(LDC93S1_BASE + ".wav", data_dir,
LDC93S1_BASE_URL + LDC93S1_BASE + ".wav")
trans_file = maybe_download(LDC93S1_BASE + ".txt", data_dir,
LDC93S1_BASE_URL + LDC93S1_BASE + ".txt")
with open(trans_file, "r") as fin:
transcript = " ".join(
fin.read().strip().lower().split(" ")[2:]).replace(".", "")
df = pandas.DataFrame(
data=[(os.path.abspath(local_file), os.path.getsize(local_file),
transcript)],
columns=["wav_filename", "wav_filesize", "transcript"],
)
df.to_csv(os.path.join(data_dir, "ldc93s1.csv"), index=False)
def _download_and_preprocess_data(target_dir, english_compatible=False):
# Making path absolute
target_dir = os.path.abspath(target_dir)
# Conditionally download data
archive_path = maybe_download("ts_" + ARCHIVE_NAME + ".zip", target_dir,
ARCHIVE_URL)
# Conditionally extract archive data
_maybe_extract(target_dir, ARCHIVE_DIR_NAME, archive_path)
# Conditionally convert TrainingSpeech data to DeepSpeech CSVs and wav
_maybe_convert_sets(target_dir,
ARCHIVE_DIR_NAME,
english_compatible=english_compatible)
def _download_and_preprocess_data(csv_url, target_dir):
dataset_sources = os.path.join(
target_dir, "transcriptionsXML_audioMP3_MEFR_CCPMF_2012-2020",
"data.txt")
if os.path.exists(dataset_sources):
return dataset_sources
# Making path absolute
target_dir = os.path.abspath(target_dir)
csv_ref = requests.get(csv_url).text.split('\r\n')[1:-1]
for part in csv_ref:
part_filename = requests.head(part).headers.get(
"Content-Disposition").split(" ")[1].split("=")[1].replace(
'"', "")
if not os.path.exists(os.path.join(target_dir, part_filename)):
part_path = maybe_download(part_filename, target_dir, part)
def _big_sha1(fname):
s = hashlib.sha1()
buffer_size = 65536
with open(fname, "rb") as f:
while True:
data = f.read(buffer_size)
if not data:
break
s.update(data)
return s.hexdigest()
for (sha1, filename) in DATASET_RELEASE_SHA:
print("Checking {} SHA1:".format(filename))
csum = _big_sha1(os.path.join(target_dir, filename))
if csum == sha1:
print("\t{}: OK {}".format(filename, sha1))
else:
print("\t{}: ERROR: expected {}, computed {}".format(
filename, sha1, csum))
assert csum == sha1
# Conditionally extract data
_maybe_extract(target_dir,
"transcriptionsXML_audioMP3_MEFR_CCPMF_2012-2020",
"transcriptionsxml_audiomp3_mefr_ccpmf_2012-2020_2.zip",
"transcriptionsXML_audioMP3_MEFR_CCPMF_2012-2020.zip")
# Produce source text for extraction / conversion
return _maybe_create_sources(
os.path.join(target_dir,
"transcriptionsXML_audioMP3_MEFR_CCPMF_2012-2020"))
def _download_and_preprocess_data(data_dir):
# Conditionally download data
TED_DATA = "TEDLIUM_release2.tar.gz"
TED_DATA_URL = "http://www.openslr.org/resources/19/TEDLIUM_release2.tar.gz"
local_file = maybe_download(TED_DATA, data_dir, TED_DATA_URL)
# Conditionally extract TED data
TED_DIR = "TEDLIUM_release2"
_maybe_extract(data_dir, TED_DIR, local_file)
# Conditionally convert TED sph data to wav
_maybe_convert_wav(data_dir, TED_DIR)
# Conditionally split TED wav and text data into sentences
train_files, dev_files, test_files = _maybe_split_sentences(
data_dir, TED_DIR)
# Write sets to disk as CSV files
train_files.to_csv(path.join(data_dir, "ted-train.csv"), index=False)
dev_files.to_csv(path.join(data_dir, "ted-dev.csv"), index=False)
test_files.to_csv(path.join(data_dir, "ted-test.csv"), index=False)
def _download_and_preprocess_data(data_dir):
# Conditionally download data to data_dir
print(
"Downloading Librivox data set (55GB) into {} if not already present...".format(
data_dir
)
)
with progressbar.ProgressBar(max_value=7, widget=progressbar.AdaptiveETA) as bar:
TRAIN_CLEAN_100_URL = (
"http://www.openslr.org/resources/12/train-clean-100.tar.gz"
)
TRAIN_CLEAN_360_URL = (
"http://www.openslr.org/resources/12/train-clean-360.tar.gz"
)
TRAIN_OTHER_500_URL = (
"http://www.openslr.org/resources/12/train-other-500.tar.gz"
)
DEV_CLEAN_URL = "http://www.openslr.org/resources/12/dev-clean.tar.gz"
DEV_OTHER_URL = "http://www.openslr.org/resources/12/dev-other.tar.gz"
TEST_CLEAN_URL = "http://www.openslr.org/resources/12/test-clean.tar.gz"
TEST_OTHER_URL = "http://www.openslr.org/resources/12/test-other.tar.gz"
def filename_of(x):
return os.path.split(x)[1]
train_clean_100 = maybe_download(
filename_of(TRAIN_CLEAN_100_URL), data_dir, TRAIN_CLEAN_100_URL
)
bar.update(0)
train_clean_360 = maybe_download(
filename_of(TRAIN_CLEAN_360_URL), data_dir, TRAIN_CLEAN_360_URL
)
bar.update(1)
train_other_500 = maybe_download(
filename_of(TRAIN_OTHER_500_URL), data_dir, TRAIN_OTHER_500_URL
)
bar.update(2)
dev_clean = maybe_download(filename_of(DEV_CLEAN_URL), data_dir, DEV_CLEAN_URL)
bar.update(3)
dev_other = maybe_download(filename_of(DEV_OTHER_URL), data_dir, DEV_OTHER_URL)
bar.update(4)
test_clean = maybe_download(
filename_of(TEST_CLEAN_URL), data_dir, TEST_CLEAN_URL
)
bar.update(5)
test_other = maybe_download(
filename_of(TEST_OTHER_URL), data_dir, TEST_OTHER_URL
)
bar.update(6)
# Conditionally extract LibriSpeech data
# We extract each archive into data_dir, but test for existence in
# data_dir/LibriSpeech because the archives share that root.
print("Extracting librivox data if not already extracted...")
with progressbar.ProgressBar(max_value=7, widget=progressbar.AdaptiveETA) as bar:
LIBRIVOX_DIR = "LibriSpeech"
work_dir = os.path.join(data_dir, LIBRIVOX_DIR)
_maybe_extract(
data_dir, os.path.join(LIBRIVOX_DIR, "train-clean-100"), train_clean_100
)
bar.update(0)
_maybe_extract(
data_dir, os.path.join(LIBRIVOX_DIR, "train-clean-360"), train_clean_360
)
bar.update(1)
_maybe_extract(
data_dir, os.path.join(LIBRIVOX_DIR, "train-other-500"), train_other_500
)
bar.update(2)
_maybe_extract(data_dir, os.path.join(LIBRIVOX_DIR, "dev-clean"), dev_clean)
bar.update(3)
_maybe_extract(data_dir, os.path.join(LIBRIVOX_DIR, "dev-other"), dev_other)
bar.update(4)
_maybe_extract(data_dir, os.path.join(LIBRIVOX_DIR, "test-clean"), test_clean)
bar.update(5)
_maybe_extract(data_dir, os.path.join(LIBRIVOX_DIR, "test-other"), test_other)
bar.update(6)
# Convert FLAC data to wav, from:
# data_dir/LibriSpeech/split/1/2/1-2-3.flac
# to:
# data_dir/LibriSpeech/split-wav/1-2-3.wav
#
# And split LibriSpeech transcriptions, from:
# data_dir/LibriSpeech/split/1/2/1-2.trans.txt
# to:
# data_dir/LibriSpeech/split-wav/1-2-0.txt
# data_dir/LibriSpeech/split-wav/1-2-1.txt
# data_dir/LibriSpeech/split-wav/1-2-2.txt
# ...
print("Converting FLAC to WAV and splitting transcriptions...")
with progressbar.ProgressBar(max_value=7, widget=progressbar.AdaptiveETA) as bar:
train_100 = _convert_audio_and_split_sentences(
work_dir, "train-clean-100", "train-clean-100-wav"
)
bar.update(0)
train_360 = _convert_audio_and_split_sentences(
work_dir, "train-clean-360", "train-clean-360-wav"
)
bar.update(1)
train_500 = _convert_audio_and_split_sentences(
work_dir, "train-other-500", "train-other-500-wav"
)
bar.update(2)
dev_clean = _convert_audio_and_split_sentences(
work_dir, "dev-clean", "dev-clean-wav"
)
bar.update(3)
dev_other = _convert_audio_and_split_sentences(
work_dir, "dev-other", "dev-other-wav"
)
bar.update(4)
test_clean = _convert_audio_and_split_sentences(
work_dir, "test-clean", "test-clean-wav"
)
bar.update(5)
test_other = _convert_audio_and_split_sentences(
work_dir, "test-other", "test-other-wav"
)
bar.update(6)
# Write sets to disk as CSV files
train_100.to_csv(
os.path.join(data_dir, "librivox-train-clean-100.csv"), index=False
)
train_360.to_csv(
os.path.join(data_dir, "librivox-train-clean-360.csv"), index=False
)
train_500.to_csv(
os.path.join(data_dir, "librivox-train-other-500.csv"), index=False
)
dev_clean.to_csv(os.path.join(data_dir, "librivox-dev-clean.csv"), index=False)
dev_other.to_csv(os.path.join(data_dir, "librivox-dev-other.csv"), index=False)
test_clean.to_csv(os.path.join(data_dir, "librivox-test-clean.csv"), index=False)
test_other.to_csv(os.path.join(data_dir, "librivox-test-other.csv"), index=False)
def download_and_prepare():
archive = maybe_download(TUDA_ARCHIVE, CLI_ARGS.base_dir, TUDA_URL)
extracted = maybe_extract(archive)
write_csvs(extracted)
cleanup(archive)
